scikit-bio

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/scikit-bio/SKILL.md

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable reference with executable code in every capability section and clean one-level-deep navigation to a real api_reference.md bundle. Its weak spots are workflow clarity (numbered pipelines lack validation/verification checkpoints for batch and statistical operations) and minor conciseness padding from repeated section scaffolding.

Suggestions

Add explicit validation/verification checkpoints to the Common Workflows (e.g. assert integer counts before beta_diversity, verify tree tips match feature IDs before UniFrac, inspect PERMANOVA p-value before interpreting), since several workflows are batch/statistical operations.

Trim the repeated 'Key operations/capabilities:'-'Common patterns:'-'Important notes:' scaffolding and the basic interop notes (e.g. 'BIOM tables are standard in QIIME 2') that Claude already knows.

Consider moving the longer per-capability code examples into references/api_reference.md so SKILL.md stays a leaner overview, leaving one representative snippet per section inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient: organized capability sections with directly usable code blocks and tight 'Important notes' bullets, but repeated per-section framing ('Key operations/capabilities:', 'Common patterns:', 'Important notes:') and occasional over-explanation of basic interop facts (e.g. BIOM 'is standard in QIIME 2 workflows') could be trimmed, keeping it just below a lean 5.	4 / 5
Actionability	Every capability section ships copy-paste-ready, executable import-and-call snippets covering the common cases (read/write, reverse_complement, nj, alpha/beta_diversity, pcoa, permanova, mantel, Table.read), with specific import paths and parameter names throughout.	5 / 5
Workflow Clarity	The 'Common Workflows' section lists four numbered end-to-end pipelines (e.g. 'Read BIOM table → Calculate alpha/beta diversity → Ordination → PERMANOVA'), but these are conceptual chains with no validation/verification checkpoints, and several involve batch/risky operations, which the guidelines cap at 3.	3 / 5
Progressive Disclosure	Good structure: SKILL.md is a capability overview with a single clearly signaled one-level reference to references/api_reference.md (a real, well-organized 749-line file with its own TOC), plus external doc links; it is not a fully lean 5 because the body inlines ten full capability sections with code that could partly live in the reference.	4 / 5
	Total	16 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A content-rich, third-person description that names many concrete scikit-bio capabilities and bioinformatics trigger terms, making it largely distinct from other skills. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when to use' half only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing biological sequences, building phylogenetic trees, computing alpha/beta diversity (UniFrac), or running ordination/PERMANOVA on microbiome data.'

Lead with concrete verbs ('Aligns sequences', 'Builds phylogenetic trees', 'Computes diversity metrics') instead of noun-phrases to raise specificity.

Include a few more natural user synonyms/extensions (e.g. '16S', 'BIOM', 'tree construction', '.fasta') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete capabilities ('Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O'), but the actions are noun-phrases rather than verbs and coverage is broad rather than granular, falling just below a comprehensive 5.	4 / 5
Completeness	It clearly answers 'what' (a biological-data toolkit with enumerated capabilities) but only ends with the weakly implied trigger 'for microbiome analysis' and no explicit 'Use when...' clause, which the guidelines cap at 3.	3 / 5
Trigger Term Quality	Strong natural technical terms ('alignments', 'phylogenetic trees', 'diversity metrics', 'UniFrac', 'PERMANOVA', 'FASTA/Newick') plus the closing 'for microbiome analysis', but missing common synonyms/extensions a user might say (e.g. 'tree', '16S', 'BIOM', '.fasta') that would earn a 5.	4 / 5
Distinctiveness Conflict Risk	The scikit-bio-specific vocabulary (UniFrac, PERMANOVA, Newick, alpha/beta diversity) carves a clear niche with minimal overlap against other skills, though it is not paired with an explicit trigger clause that would make it a 5.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/scikit-bio/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.